Towards Lossless Head Pruning through Automatic Peer Distillation for Language Models.
Bingbing LiZigeng WangShaoyi HuangMikhail A. BraginJi LiCaiwen DingPublished in: IJCAI (2023)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- document retrieval
- context sensitive
- statistical language models
- information retrieval
- query expansion
- speech recognition
- language modelling
- retrieval model
- pseudo relevance feedback
- language model for information retrieval
- language models for information retrieval
- relevance model
- test collection
- document ranking
- term dependencies
- smoothing methods
- ad hoc information retrieval
- statistical language modeling
- vector space model
- document collections